Class 12

Question 1

computer vision

Answer 1

perceptual channel that accepts a stimulus and reports some representation of the world

Question 2

passive sensing

Answer 2

type of vision that most agents use where they don’t need to send out light to see

Question 3

feature

Answer 3

number obtained by applying simple computations to an image

Question 4

feature extraction

Answer 4

process of applying direct computation to sensor responses

Question 5

object model

Answer 5

precise geometric model produced by computer aided design systems

Question 6

rendering model

Answer 6

describes the physical, geometric, and statistical processes that produce the stimulus from the word

Question 7

reconstruction

Answer 7

when an agent builds a model of the world from an image or images

Question 8

recognition

Answer 8

term for drawing distinctions among objects based on visual and other information

Question 9

pinhole camera

Answer 9

simplest way to form a focused image of a stationary object

Question 10

aperture

Answer 10

opening or “pinhole”

Question 11

motion blur

Answer 11

object is moving and the time window is large enough

Question 12

focal length

Answer 12

distance between lens and the image sensor

Question 13

focal plane

Answer 13

plane in the environment where the focus is sharpest

Question 14

scaled orthographic projection

Answer 14

used to handle geometric effect of perspective imaging that aren’t always pronounced

Question 15

diffuse reflection

Answer 15

light is scattered evenly in all directions – how most surfaces reflect light

Question 16

specular reflection

Answer 16

causes incoming light to leave a surface in a lobe of directions that is determined by the direction the light arrived from

Question 17

specularities

Answer 17

small bright patches found on rougher surfaces

Question 18

lamberts cosine law

Answer 18

brightness of a diffuse patch

Question 19

interreflections

Answer 19

light reflected from other surfaces which illuminates shadowed patches

Question 20

principle of trichromacy

Answer 20

humans of 3 types of color sensitive receptors

Question 21

edge

Answer 21

straight line or curve in image plane across which there is a significant change in image brightness

Question 22

texture

Answer 22

pattern on a surface that can be sensed visually

Question 23

texels

Answer 23

rough model of texture that is a repetitive pattern of elements

Question 24

optical flow

Answer 24

whenever there is relative movement between the camera and 1 or more objects in the scene resulting in apparent motion

Question 25

segmentation

Answer 25

process of breaking an image into groups of similar pixels

Question 26

regions

Answer 26

generalized groupings of segments once edges have been determined – aka superpixels

Question 27

convolutional neural networks

Answer 27

excellent image classifier, pooling layers reduce spatial dimensions of input

Question 28

regional proposal network

Answer 28

network that finds regions with objects

Question 29

region of interest

Answer 29

a box with a good enough objectness score

Question 30

roi pooling

Answer 30

process of sampling pixels to extract features

Question 31

bounding box regression

Answer 31

step that trims the window down to a proper bounding box

Question 32

disparity

Answer 32

the shifting of one view to another view

Question 33

tagging systems

Answer 33

tag images with relevant words

Question 34

depth map

Answer 34

an array giving the depth of each pixel

Question 35

style transfer

Answer 35

involves taking 2 images with content and style and transferring the content of one onto the style of the other